Google DeepMind Releases Gemma 4 12B: An Encoder-Free Multimodal Model with Native audio that runs on a 16 GB laptop
Google DeepMind has released Gemma 4 12B, an open-source multimodal AI model capable of processing text, images, audio, and video natively. This model is designed to run on consumer laptops with as little as 16 GB of RAM, significantly reducing hardware requirements. Its unique encoder-free architecture allows for direct input of various modalities into the language model backbone, leading to lower latency and memory usage. Gemma 4 12B is available under the Apache 2.0 license, enabling commercial use and further development by the community. AI
IMPACT Enables advanced multimodal AI capabilities on consumer hardware, potentially accelerating local AI agent development and adoption.